July 28, 2019

3158 words 15 mins read

Paper Group ANR 377

Meta-Learning MCMC Proposals. A Supervised STDP-based Training Algorithm for Living Neural Networks. Single-pixel imaging with Morlet wavelet correlated random patterns. A generalized multivariate Student-t mixture model for Bayesian classification and clustering of radar waveforms. Post-hoc labeling of arbitrary EEG recordings for data-efficient e …

Meta-Learning MCMC Proposals


Title	Meta-Learning MCMC Proposals
Authors	Tongzhou Wang, Yi Wu, David A. Moore, Stuart J. Russell
Abstract	Effective implementations of sampling-based probabilistic inference often require manually constructed, model-specific proposals. Inspired by recent progresses in meta-learning for training learning agents that can generalize to unseen environments, we propose a meta-learning approach to building effective and generalizable MCMC proposals. We parametrize the proposal as a neural network to provide fast approximations to block Gibbs conditionals. The learned neural proposals generalize to occurrences of common structural motifs across different models, allowing for the construction of a library of learned inference primitives that can accelerate inference on unseen models with no model-specific training required. We explore several applications including open-universe Gaussian mixture models, in which our learned proposals outperform a hand-tuned sampler, and a real-world named entity recognition task, in which our sampler yields higher final F1 scores than classical single-site Gibbs sampling.
Tasks	Meta-Learning, Named Entity Recognition
Published	2017-08-21
URL	http://arxiv.org/abs/1708.06040v5
PDF	http://arxiv.org/pdf/1708.06040v5.pdf
PWC	https://paperswithcode.com/paper/meta-learning-mcmc-proposals
Repo
Framework

A Supervised STDP-based Training Algorithm for Living Neural Networks


Title	A Supervised STDP-based Training Algorithm for Living Neural Networks
Authors	Yuan Zeng, Kevin Devincentis, Yao Xiao, Zubayer Ibne Ferdous, Xiaochen Guo, Zhiyuan Yan, Yevgeny Berdichevsky
Abstract	Neural networks have shown great potential in many applications like speech recognition, drug discovery, image classification, and object detection. Neural network models are inspired by biological neural networks, but they are optimized to perform machine learning tasks on digital computers. The proposed work explores the possibilities of using living neural networks in vitro as basic computational elements for machine learning applications. A new supervised STDP-based learning algorithm is proposed in this work, which considers neuron engineering constrains. A 74.7% accuracy is achieved on the MNIST benchmark for handwritten digit recognition.
Tasks	Drug Discovery, Handwritten Digit Recognition, Image Classification, Object Detection, Speech Recognition
Published	2017-10-30
URL	http://arxiv.org/abs/1710.10944v3
PDF	http://arxiv.org/pdf/1710.10944v3.pdf
PWC	https://paperswithcode.com/paper/a-supervised-stdp-based-training-algorithm
Repo
Framework

Single-pixel imaging with Morlet wavelet correlated random patterns


Title	Single-pixel imaging with Morlet wavelet correlated random patterns
Authors	Krzysztof M. Czajkowski, Anna Pastuszczak, Rafał Kotyński
Abstract	Single-pixel imaging is an indirect imaging technique which utilizes simplified optical hardware and advanced computational methods. It offers novel solutions for hyper-spectral imaging, polarimetric imaging, three-dimensional imaging, holographic imaging, optical encryption and imaging through scattering media. The main limitations for its use come from relatively high measurement and reconstruction times. In this paper we propose to reduce the required signal acquisition time by using a novel sampling scheme based on a random selection of Morlet wavelets convolved with white noise. While such functions exhibit random properties, they are locally determined by Morlet wavelet parameters. The proposed method is equivalent to random sampling of the properly selected part of the feature space, which maps the measured images accurately both in the spatial and spatial frequency domains. We compare both numerically and experimentally the image quality obtained with our sampling protocol against widely-used sampling with Walsh-Hadamard or noiselet functions. The results show considerable improvement over the former methods, enabling single-pixel imaging at low compression rates on the order of a few percent.
Tasks
Published	2017-09-22
URL	http://arxiv.org/abs/1709.07739v2
PDF	http://arxiv.org/pdf/1709.07739v2.pdf
PWC	https://paperswithcode.com/paper/single-pixel-imaging-with-morlet-wavelet
Repo
Framework

A generalized multivariate Student-t mixture model for Bayesian classification and clustering of radar waveforms


Title	A generalized multivariate Student-t mixture model for Bayesian classification and clustering of radar waveforms
Authors	Guillaume Revillon, Ali Mohammad-Djafari, Cyrille Enderli
Abstract	In this paper, a generalized multivariate Student-t mixture model is developed for classification and clustering of Low Probability of Intercept radar waveforms. A Low Probability of Intercept radar signal is characterized by a pulse compression waveform which is either frequency-modulated or phase-modulated. The proposed model can classify and cluster different modulation types such as linear frequency modulation, non linear frequency modulation, polyphase Barker, polyphase P1, P2, P3, P4, Frank and Zadoff codes. The classification method focuses on the introduction of a new prior distribution for the model hyper-parameters that gives us the possibility to handle sensitivity of mixture models to initialization and to allow a less restrictive modeling of data. Inference is processed through a Variational Bayes method and a Bayesian treatment is adopted for model learning, supervised classification and clustering. Moreover, the novel prior distribution is not a well-known probability distribution and both deterministic and stochastic methods are employed to estimate its expectations. Some numerical experiments show that the proposed method is less sensitive to initialization and provides more accurate results than the previous state of the art mixture models.
Tasks
Published	2017-07-29
URL	http://arxiv.org/abs/1707.09548v1
PDF	http://arxiv.org/pdf/1707.09548v1.pdf
PWC	https://paperswithcode.com/paper/a-generalized-multivariate-student-t-mixture
Repo
Framework

Post-hoc labeling of arbitrary EEG recordings for data-efficient evaluation of neural decoding methods


Title	Post-hoc labeling of arbitrary EEG recordings for data-efficient evaluation of neural decoding methods
Authors	Sebastian Castaño-Candamil, Andreas Meinel, Michael Tangermann
Abstract	Many cognitive, sensory and motor processes have correlates in oscillatory neural sources, which are embedded as a subspace into the recorded brain signals. Decoding such processes from noisy magnetoencephalogram/electroencephalogram (M/EEG) signals usually requires the use of data-driven analysis methods. The objective evaluation of such decoding algorithms on experimental raw signals, however, is a challenge: the amount of available M/EEG data typically is limited, labels can be unreliable, and raw signals often are contaminated with artifacts. The latter is specifically problematic, if the artifacts stem from behavioral confounds of the oscillatory neural processes of interest. To overcome some of these problems, simulation frameworks have been introduced for benchmarking decoding methods. Generating artificial brain signals, however, most simulation frameworks make strong and partially unrealistic assumptions about brain activity, which limits the generalization of obtained results to real-world conditions. In the present contribution, we thrive to remove many shortcomings of current simulation frameworks and propose a versatile alternative, that allows for objective evaluation and benchmarking of novel data-driven decoding methods for neural signals. Its central idea is to utilize post-hoc labelings of arbitrary M/EEG recordings. This strategy makes it paradigm-agnostic and allows to generate comparatively large datasets with noiseless labels. Source code and data of the novel simulation approach are made available for facilitating its adoption.
Tasks	EEG
Published	2017-11-22
URL	http://arxiv.org/abs/1711.08208v1
PDF	http://arxiv.org/pdf/1711.08208v1.pdf
PWC	https://paperswithcode.com/paper/post-hoc-labeling-of-arbitrary-eeg-recordings
Repo
Framework

What’s In A Patch, I: Tensors, Differential Geometry and Statistical Shading Analysis


Title	What’s In A Patch, I: Tensors, Differential Geometry and Statistical Shading Analysis
Authors	Daniel Niels Holtmann-Rice, Benjamin S. Kunsberg, Steven W. Zucker
Abstract	We develop a linear algebraic framework for the shape-from-shading problem, because tensors arise when scalar (e.g. image) and vector (e.g. surface normal) fields are differentiated multiple times. The work is in two parts. In this first part we investigate when image derivatives exhibit invariance to changing illumination by calculating the statistics of image derivatives under general distributions on the light source. We computationally validate the hypothesis that image orientations (derivatives) provide increased invariance to illumination by showing (for a Lambertian model) that a shape-from-shading algorithm matching gradients instead of intensities provides more accurate reconstructions when illumination is incorrectly estimated under a flatness prior.
Tasks
Published	2017-05-16
URL	http://arxiv.org/abs/1705.05885v1
PDF	http://arxiv.org/pdf/1705.05885v1.pdf
PWC	https://paperswithcode.com/paper/whats-in-a-patch-i-tensors-differential
Repo
Framework

Clustering with Noisy Queries


Title	Clustering with Noisy Queries
Authors	Arya Mazumdar, Barna Saha
Abstract	In this paper, we initiate a rigorous theoretical study of clustering with noisy queries (or a faulty oracle). Given a set of $n$ elements, our goal is to recover the true clustering by asking minimum number of pairwise queries to an oracle. Oracle can answer queries of the form : “do elements $u$ and $v$ belong to the same cluster?” – the queries can be asked interactively (adaptive queries), or non-adaptively up-front, but its answer can be erroneous with probability $p$. In this paper, we provide the first information theoretic lower bound on the number of queries for clustering with noisy oracle in both situations. We design novel algorithms that closely match this query complexity lower bound, even when the number of clusters is unknown. Moreover, we design computationally efficient algorithms both for the adaptive and non-adaptive settings. The problem captures/generalizes multiple application scenarios. It is directly motivated by the growing body of work that use crowdsourcing for {\em entity resolution}, a fundamental and challenging data mining task aimed to identify all records in a database referring to the same entity. Here crowd represents the noisy oracle, and the number of queries directly relates to the cost of crowdsourcing. Another application comes from the problem of {\em sign edge prediction} in social network, where social interactions can be both positive and negative, and one must identify the sign of all pair-wise interactions by querying a few pairs. Furthermore, clustering with noisy oracle is intimately connected to correlation clustering, leading to improvement therein. Finally, it introduces a new direction of study in the popular {\em stochastic block model} where one has an incomplete stochastic block model matrix to recover the clusters.
Tasks	Entity Resolution
Published	2017-06-22
URL	http://arxiv.org/abs/1706.07510v1
PDF	http://arxiv.org/pdf/1706.07510v1.pdf
PWC	https://paperswithcode.com/paper/clustering-with-noisy-queries
Repo
Framework

Deep Convolutional Neural Networks as Generic Feature Extractors


Title	Deep Convolutional Neural Networks as Generic Feature Extractors
Authors	Lars Hertel, Erhardt Barth, Thomas Käster, Thomas Martinetz
Abstract	Recognizing objects in natural images is an intricate problem involving multiple conflicting objectives. Deep convolutional neural networks, trained on large datasets, achieve convincing results and are currently the state-of-the-art approach for this task. However, the long time needed to train such deep networks is a major drawback. We tackled this problem by reusing a previously trained network. For this purpose, we first trained a deep convolutional network on the ILSVRC2012 dataset. We then maintained the learned convolution kernels and only retrained the classification part on different datasets. Using this approach, we achieved an accuracy of 67.68 % on CIFAR-100, compared to the previous state-of-the-art result of 65.43 %. Furthermore, our findings indicate that convolutional networks are able to learn generic feature extractors that can be used for different tasks.
Tasks	Image Classification
Published	2017-10-06
URL	http://arxiv.org/abs/1710.02286v1
PDF	http://arxiv.org/pdf/1710.02286v1.pdf
PWC	https://paperswithcode.com/paper/deep-convolutional-neural-networks-as-generic
Repo
Framework

Learning Video Object Segmentation with Visual Memory


Title	Learning Video Object Segmentation with Visual Memory
Authors	Pavel Tokmakov, Karteek Alahari, Cordelia Schmid
Abstract	This paper addresses the task of segmenting moving objects in unconstrained videos. We introduce a novel two-stream neural network with an explicit memory module to achieve this. The two streams of the network encode spatial and temporal features in a video sequence respectively, while the memory module captures the evolution of objects over time. The module to build a “visual memory” in video, i.e., a joint representation of all the video frames, is realized with a convolutional recurrent unit learned from a small number of training video sequences. Given a video frame as input, our approach assigns each pixel an object or background label based on the learned spatio-temporal features as well as the “visual memory” specific to the video, acquired automatically without any manually-annotated frames. The visual memory is implemented with convolutional gated recurrent units, which allows to propagate spatial information over time. We evaluate our method extensively on two benchmarks, DAVIS and Freiburg-Berkeley motion segmentation datasets, and show state-of-the-art results. For example, our approach outperforms the top method on the DAVIS dataset by nearly 6%. We also provide an extensive ablative analysis to investigate the influence of each component in the proposed framework.
Tasks	Motion Segmentation, Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation
Published	2017-04-19
URL	http://arxiv.org/abs/1704.05737v2
PDF	http://arxiv.org/pdf/1704.05737v2.pdf
PWC	https://paperswithcode.com/paper/learning-video-object-segmentation-with
Repo
Framework

The 2017 DAVIS Challenge on Video Object Segmentation


Title	The 2017 DAVIS Challenge on Video Object Segmentation
Authors	Jordi Pont-Tuset, Federico Perazzi, Sergi Caelles, Pablo Arbeláez, Alex Sorkine-Hornung, Luc Van Gool
Abstract	We present the 2017 DAVIS Challenge on Video Object Segmentation, a public dataset, benchmark, and competition specifically designed for the task of video object segmentation. Following the footsteps of other successful initiatives, such as ILSVRC and PASCAL VOC, which established the avenue of research in the fields of scene classification and semantic segmentation, the DAVIS Challenge comprises a dataset, an evaluation methodology, and a public competition with a dedicated workshop co-located with CVPR 2017. The DAVIS Challenge follows up on the recent publication of DAVIS (Densely-Annotated VIdeo Segmentation), which has fostered the development of several novel state-of-the-art video object segmentation techniques. In this paper we describe the scope of the benchmark, highlight the main characteristics of the dataset, define the evaluation metrics of the competition, and present a detailed analysis of the results of the participants to the challenge.
Tasks	Scene Classification, Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00675v3
PDF	http://arxiv.org/pdf/1704.00675v3.pdf
PWC	https://paperswithcode.com/paper/the-2017-davis-challenge-on-video-object
Repo
Framework

Dynamic State Warping


Title	Dynamic State Warping
Authors	Zhichen Gong, Huanhuan Chen
Abstract	The ubiquity of sequences in many domains enhances significant recent interest in sequence learning, for which a basic problem is how to measure the distance between sequences. Dynamic time warping (DTW) aligns two sequences by nonlinear local warping and returns a distance value. DTW shows superior ability in many applications, e.g. video, image, etc. However, in DTW, two points are paired essentially based on point-to-point Euclidean distance (ED) without considering the autocorrelation of sequences. Thus, points with different semantic meanings, e.g. peaks and valleys, may be matched providing their coordinate values are similar. As a result, DTW is sensitive to noise and poorly interpretable. This paper proposes an efficient and flexible sequence alignment algorithm, dynamic state warping (DSW). DSW converts each time point into a latent state, which endows point-wise autocorrelation information. Alignment is performed by using the state sequences. Thus DSW is able to yield alignment that is semantically more interpretable than that of DTW. Using one nearest neighbor classifier, DSW shows significant improvement on classification accuracy in comparison to ED (70/85 wins) and DTW (74/85 wins). We also empirically demonstrate that DSW is more robust and scales better to long sequences than ED and DTW.
Tasks
Published	2017-03-03
URL	http://arxiv.org/abs/1703.01141v1
PDF	http://arxiv.org/pdf/1703.01141v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-state-warping
Repo
Framework

Cloud-based or On-device: An Empirical Study of Mobile Deep Inference


Title	Cloud-based or On-device: An Empirical Study of Mobile Deep Inference
Authors	Tian Guo
Abstract	Modern mobile applications are benefiting significantly from the advancement in deep learning, e.g., implementing real-time image recognition and conversational system. Given a trained deep learning model, applications usually need to perform a series of matrix operations based on the input data, in order to infer possible output values. Because of computational complexity and size constraints, these trained models are often hosted in the cloud. To utilize these cloud-based models, mobile apps will have to send input data over the network. While cloud-based deep learning can provide reasonable response time for mobile apps, it restricts the use case scenarios, e.g. mobile apps need to have network access. With mobile specific deep learning optimizations, it is now possible to employ on-device inference. However, because mobile hardware, such as GPU and memory size, can be very limited when compared to its desktop counterpart, it is important to understand the feasibility of this new on-device deep learning inference architecture. In this paper, we empirically evaluate the inference performance of three Convolutional Neural Networks (CNNs) using a benchmark Android application we developed. Our measurement and analysis suggest that on-device inference can cost up to two orders of magnitude greater response time and energy when compared to cloud-based inference, and that loading model and computing probability are two performance bottlenecks for on-device deep inferences.
Tasks
Published	2017-07-14
URL	http://arxiv.org/abs/1707.04610v2
PDF	http://arxiv.org/pdf/1707.04610v2.pdf
PWC	https://paperswithcode.com/paper/cloud-based-or-on-device-an-empirical-study
Repo
Framework

Coresets for Triangulation


Title	Coresets for Triangulation
Authors	Qianggong Zhang, Tat-Jun Chin
Abstract	Multiple-view triangulation by $\ell_{\infty}$ minimisation has become established in computer vision. State-of-the-art $\ell_{\infty}$ triangulation algorithms exploit the quasiconvexity of the cost function to derive iterative update rules that deliver the global minimum. Such algorithms, however, can be computationally costly for large problem instances that contain many image measurements, e.g., from web-based photo sharing sites or long-term video recordings. In this paper, we prove that $\ell_{\infty}$ triangulation admits a coreset approximation scheme, which seeks small representative subsets of the input data called coresets. A coreset possesses the special property that the error of the $\ell_{\infty}$ solution on the coreset is within known bounds from the global minimum. We establish the necessary mathematical underpinnings of the coreset algorithm, specifically, by enacting the stopping criterion of the algorithm and proving that the resulting coreset gives the desired approximation accuracy. On large-scale triangulation problems, our method provides theoretically sound approximate solutions. Iterated until convergence, our coreset algorithm is also guaranteed to reach the true optimum. On practical datasets, we show that our technique can in fact attain the global minimiser much faster than current methods
Tasks
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05466v1
PDF	http://arxiv.org/pdf/1707.05466v1.pdf
PWC	https://paperswithcode.com/paper/coresets-for-triangulation
Repo
Framework

Detecting and assessing contextual change in diachronic text documents using context volatility


Title	Detecting and assessing contextual change in diachronic text documents using context volatility
Authors	Christian Kahmann, Andreas Niekler, Gerhard Heyer
Abstract	Terms in diachronic text corpora may exhibit a high degree of semantic dynamics that is only partially captured by the common notion of semantic change. The new measure of context volatility that we propose models the degree by which terms change context in a text collection over time. The computation of context volatility for a word relies on the significance-values of its co-occurrent terms and the corresponding co-occurrence ranks in sequential time spans. We define a baseline and present an efficient computational approach in order to overcome problems related to computational issues in the data structure. Results are evaluated both, on synthetic documents that are used to simulate contextual changes, and a real example based on British newspaper texts.
Tasks
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05538v1
PDF	http://arxiv.org/pdf/1711.05538v1.pdf
PWC	https://paperswithcode.com/paper/detecting-and-assessing-contextual-change-in
Repo
Framework

A Maximal Heterogeneity Based Clustering Approach for Obtaining Samples


Title	A Maximal Heterogeneity Based Clustering Approach for Obtaining Samples
Authors	Megha Mishra, Chandrasekaran Anirudh Bhardwaj, Kalyani Desikan
Abstract	Medical and social sciences demand sampling techniques which are robust, reliable, replicable and have the least dissimilarity between the samples obtained. Majority of the applications of sampling use randomized sampling, albeit with stratification where applicable. The randomized technique is not consistent, and may provide different samples each time, and the different samples themselves may not be similar to each other. In this paper, we introduce a novel non-statistical no-replacement sampling technique called Wobbly Center Algorithm, which relies on building clusters iteratively based on maximizing the heterogeneity inside each cluster. The algorithm works on the principle of stepwise building of clusters by finding the points with the maximal distance from the cluster center. The obtained results are validated statistically using Analysis of Variance tests by comparing the samples obtained to check if they are representative of each other. The obtained results generated from running the Wobbly Center algorithm on benchmark datasets when compared against other sampling algorithms indicate the superiority of the Wobbly Center Algorithm.
Tasks
Published	2017-09-02
URL	http://arxiv.org/abs/1709.01423v3
PDF	http://arxiv.org/pdf/1709.01423v3.pdf
PWC	https://paperswithcode.com/paper/a-maximal-heterogeneity-based-clustering
Repo
Framework